谷歌CVPR最全总结：45篇论文，Ian Goodfellow GAN演讲PPT下载

针对像素级的上下文注意力，以检测显著性PiCANet: Learning Pixel-wise Contextual Attention for Saliency DetectionNian Liu, Junwei Han, Ming-Hsuan Yang机器人和驾驶中的计算机视觉Computer Vision for Robotics and DrivingAnelia Angelova, Sanja Fidler无监督视觉学习Unsupervised Visual LearningPierre Sermanet, Anelia AngelovaUltraFast 3D感应，重建和理解人物、物体和环境UltraFast 3D Sensing, Reconstruction and Understanding of People, Objects and EnvironmentsSean Fanello, Julien Valentin, Jonathan Taylor, Christoph Rhemann, Adarsh Kowdle, Jürgen Sturm, Christine Kaeser-Chen, Pavel Pidlypenskyi, Rohit Pandey, Andrea Tagliasacchi, Sameh Khamis, David Kim, Mingsong Dou, Kaiwen Guo, Danhang Tang, Shahram Izadi生成对抗网络Generative Adversarial NetworksJun-Yan Zhu, Taesung Park, Mihaela Rosca, Phillip Isola, Ian GoodfellowIan Goodfellowa：生成对抗网络（35 PPT）生成建模：密度估计生成建模：样本生成训练数据（CelebA）→样本生成对抗网络的框架Self-Attention GANImageNet上最优的FID：1000个类别，128x128 像素Self-Play用GAN能做什么呢？自动驾驶数据集用于模拟训练数据的GANGAN用于缺失数据GAN用于半监督学习用于半监督学习的有监督鉴别器半监督分类GAN用于下一帧视频的预测GAN用于逼真的生成任务GAN用于基于模型的优化GAN用于自动化定制GAN用于域自适应GAN的一些技巧